The TX path may release the dmabuf in a context where we cannot wait. This happens when the user unbinds a TX dmabuf while there are still references to its netmems in the TX path. In that case, the netmems will be put_netmem'd from a context where we can't unmap the dmabuf, resulting in a BUG like seen by Stan:
[ 1.548495] BUG: sleeping function called from invalid context at drivers/dma-buf/dma-buf.c:1255 [ 1.548741] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 149, name: ncdevmem [ 1.548926] preempt_count: 201, expected: 0 [ 1.549026] RCU nest depth: 0, expected: 0 [ 1.549197] [ 1.549237] ============================= [ 1.549331] [ BUG: Invalid wait context ] [ 1.549425] 6.13.0-rc3-00770-gbc9ef9606dc9-dirty #15 Tainted: G W [ 1.549609] ----------------------------- [ 1.549704] ncdevmem/149 is trying to lock: [ 1.549801] ffff8880066701c0 (reservation_ww_class_mutex){+.+.}-{4:4}, at: dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.550051] other info that might help us debug this: [ 1.550167] context-{5:5} [ 1.550229] 3 locks held by ncdevmem/149: [ 1.550322] #0: ffff888005730208 (&sb->s_type->i_mutex_key#11){+.+.}-{4:4}, at: sock_close+0x40/0xf0 [ 1.550530] #1: ffff88800b148f98 (sk_lock-AF_INET6){+.+.}-{0:0}, at: tcp_close+0x19/0x80 [ 1.550731] #2: ffff88800b148f18 (slock-AF_INET6){+.-.}-{3:3}, at: __tcp_close+0x185/0x4b0 [ 1.550921] stack backtrace: [ 1.550990] CPU: 0 UID: 0 PID: 149 Comm: ncdevmem Tainted: G W 6.13.0-rc3-00770-gbc9ef9606dc9-dirty #15 [ 1.551233] Tainted: [W]=WARN [ 1.551304] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014 [ 1.551518] Call Trace: [ 1.551584] <TASK> [ 1.551636] dump_stack_lvl+0x86/0xc0 [ 1.551723] __lock_acquire+0xb0f/0xc30 [ 1.551814] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.551941] lock_acquire+0xf1/0x2a0 [ 1.552026] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552152] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552281] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552408] __ww_mutex_lock+0x121/0x1060 [ 1.552503] ? dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552648] ww_mutex_lock+0x3d/0xa0 [ 1.552733] dma_buf_unmap_attachment_unlocked+0x4b/0x90 [ 1.552857] __net_devmem_dmabuf_binding_free+0x56/0xb0 [ 1.552979] skb_release_data+0x120/0x1f0 [ 1.553074] __kfree_skb+0x29/0xa0 [ 1.553156] tcp_write_queue_purge+0x41/0x310 [ 1.553259] tcp_v4_destroy_sock+0x127/0x320 [ 1.553363] ? __tcp_close+0x169/0x4b0 [ 1.553452] inet_csk_destroy_sock+0x53/0x130 [ 1.553560] __tcp_close+0x421/0x4b0 [ 1.553646] tcp_close+0x24/0x80 [ 1.553724] inet_release+0x5d/0x90 [ 1.553806] sock_close+0x4a/0xf0 [ 1.553886] __fput+0x9c/0x2b0 [ 1.553960] task_work_run+0x89/0xc0 [ 1.554046] do_exit+0x27f/0x980 [ 1.554125] do_group_exit+0xa4/0xb0 [ 1.554211] __x64_sys_exit_group+0x17/0x20 [ 1.554309] x64_sys_call+0x21a0/0x21a0 [ 1.554400] do_syscall_64+0xec/0x1d0 [ 1.554487] ? exc_page_fault+0x8a/0xf0 [ 1.554585] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 1.554703] RIP: 0033:0x7f2f8a27abcd
Resolve this by making __net_devmem_dmabuf_binding_free schedule_work'd.
Suggested-by: Stanislav Fomichev sdf@fomichev.me Signed-off-by: Mina Almasry almasrymina@google.com
--- net/core/devmem.c | 4 +++- net/core/devmem.h | 10 ++++++---- 2 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/net/core/devmem.c b/net/core/devmem.c index 796338b1599e..58fcae0c0c69 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -46,8 +46,10 @@ static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov) ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); }
-void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +void __net_devmem_dmabuf_binding_free(struct work_struct *wq) { + struct net_devmem_dmabuf_binding *binding = container_of(wq, typeof(*binding), unbind_w); + size_t size, avail;
gen_pool_for_each_chunk(binding->chunk_pool, diff --git a/net/core/devmem.h b/net/core/devmem.h index 874e891e70e0..63d16dbaca2d 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -52,6 +52,8 @@ struct net_devmem_dmabuf_binding { * net_iovs in the TX path. */ struct net_iov **tx_vec; + + struct work_struct unbind_w; };
#if defined(CONFIG_NET_DEVMEM) @@ -74,7 +76,7 @@ struct dmabuf_genpool_chunk_owner { struct net_devmem_dmabuf_binding *binding; };
-void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +void __net_devmem_dmabuf_binding_free(struct work_struct *wq); struct net_devmem_dmabuf_binding * net_devmem_bind_dmabuf(struct net_device *dev, enum dma_data_direction direction, @@ -129,7 +131,8 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) if (!refcount_dec_and_test(&binding->ref)) return;
- __net_devmem_dmabuf_binding_free(binding); + INIT_WORK(&binding->unbind_w, __net_devmem_dmabuf_binding_free); + schedule_work(&binding->unbind_w); }
void net_devmem_get_net_iov(struct net_iov *niov); @@ -161,8 +164,7 @@ static inline void net_devmem_put_net_iov(struct net_iov *niov) { }
-static inline void -__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +static inline void __net_devmem_dmabuf_binding_free(struct work_struct *wq) { }